WO2020126338A1 - Procédé et système servant à déterminer une trajectoire corrigée d'un véhicule - Google Patents

Procédé et système servant à déterminer une trajectoire corrigée d'un véhicule Download PDF

Info

Publication number
WO2020126338A1
WO2020126338A1 PCT/EP2019/082485 EP2019082485W WO2020126338A1 WO 2020126338 A1 WO2020126338 A1 WO 2020126338A1 EP 2019082485 W EP2019082485 W EP 2019082485W WO 2020126338 A1 WO2020126338 A1 WO 2020126338A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
trajectory section
trajectory
detected
section
Prior art date
Application number
PCT/EP2019/082485
Other languages
German (de)
English (en)
Inventor
Moritz Schack
Christian MERFELS
Original Assignee
Volkswagen Aktiengesellschaft
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Volkswagen Aktiengesellschaft filed Critical Volkswagen Aktiengesellschaft
Priority to CN201980083784.XA priority Critical patent/CN113165661A/zh
Priority to EP19816216.6A priority patent/EP3898368B1/fr
Publication of WO2020126338A1 publication Critical patent/WO2020126338A1/fr

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0225—Failure correction strategy
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0083—Setting, resetting, calibration
    • B60W2050/0088—Adaptive recalibration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • B60W2050/0215—Sensor drifts or sensor failures
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/45—External transmission of data to or from the vehicle
    • B60W2556/50—External transmission of data to or from the vehicle of positioning data, e.g. GPS [Global Positioning System] data

Definitions

  • the present invention relates to a method for determining a trajectory of a
  • map data are provided about a traffic route on which the vehicle is moving, the map data comprising a preferred line for driving on the traffic route.
  • a trajectory section of the vehicle is detected.
  • the invention further relates to a position determination system for determining a trajectory of a vehicle.
  • the system comprises a map data providing unit for providing map data about a traffic route on which the vehicle is moving, the map data comprising a preferred line for driving on the traffic route. It also includes one
  • Position determination unit for detecting a trajectory section of the vehicle and a computing unit coupled to the position determination unit and the map data preparation unit.
  • Modern vehicles often include a large number of driver assistance systems that support the control of the vehicle and allow automation of driving functions to varying degrees. This can go as far as fully autonomous control of the vehicle.
  • Many driver assistance functions require highly precise knowledge of the global vehicle position.
  • the relative position to a digital map with lane information is of particular interest, for example for determining the relative position of the vehicle to the center of the lane. It has been shown that the detected position is very often shifted with respect to a highly precise map-based reference system.
  • GNSS global navigation satellite systems
  • Map-based location systems can have an offset due to insufficient calibration of the sensors used (e.g. lidar, cameras, radar) or due to defective map material.
  • the position estimates of location systems therefore often have an offset that is more or less constant over a certain period of time.
  • the time period depends on concrete location system and its environmental conditions.
  • GPS global positioning system
  • GPS systems with an accuracy in the centimeter range can be used, such as an RTK GPS system or systems with terrestrial correction data.
  • RTK GPS system or systems with terrestrial correction data.
  • Similar reference systems are also available based on imaging sensors.
  • US 2017/0247032 A1 describes a method in which a corrected path is determined for a vehicle with a trailer in order to follow the course of a curve.
  • map-based lanes This data is used to determine which lane the vehicle is on.
  • An image capture unit detects road markings and it is also determined whether these data are sufficient to determine the lateral position.
  • DE 10 2017 006 142 A1 describes a method for localizing a vehicle within a lane, in which a particle filter and a
  • Odometric model the most likely position is estimated.
  • a map with center lines Using a map with center lines, a map with polygons can also be generated and for determining the
  • the present invention has for its object to provide a method and a system of the type mentioned, which allow a particularly precise determination of the trajectory traveled by the vehicle with simple means.
  • the method according to the invention of the type mentioned at the outset is characterized in that a location offset is determined on the basis of a comparison of the detected trajectory section and the preferred line. Based on the location offset and the recorded
  • a corrected trajectory section is determined in the trajectory section, the location offset being determined in such a way that a deviation between the preferred line and the corrected trajectory section is optimized.
  • the method is based on the assumption that the vehicle is actually actually moving along the preferred line.
  • a trajectory section is considered as a whole, so that temporary deviations from the preferred line can be compensated for by averaging over a longer period or a longer distance.
  • an entire section of the trajectory traveled by the vehicle is therefore taken into account instead of a correction between the detected position and the actual position only for a single position.
  • the course of the trajectory section can also be used in the invention, for example in the case of a non-linear movement, in order to determine the location offset particularly precisely.
  • the map data are provided in a manner known per se, for example by means of a navigation system or a storage unit of the vehicle. They can also be provided by an external unit, such as an external server, from which the required map data for a specific geographical area is retrieved when the vehicle is approaching or moving within the area, or when a planned travel of the vehicle is through this area.
  • an external unit such as an external server
  • the map data include in particular information about a geographical classification of the traffic route and about lanes that are formed on the traffic route.
  • the map data include a geometric description of the traffic route,
  • the preferred line in the sense of the invention denotes a line along the longitudinal extent of the traffic route. For example, it describes a trajectory along which the vehicle can move on the traffic route. In particular, it is about
  • the preferred line can extend, for example, in the geometric center of a lane along its longitudinal course. It can also be a theoretical trajectory of a vehicle
  • the preferred line can already be encompassed by the map data, which are provided, for example, by a navigation system. Alternatively or additionally, a
  • Preprocessing of the provided map data can be provided, in which the execution line is generated, for example by a preprocessing unit of the vehicle.
  • the preferred line can also be designed as a planned trajectory of the vehicle, in particular for autonomous control of the vehicle.
  • the trajectory section of the vehicle is recorded in a manner known per se,
  • GPS global navigation satellite system
  • the trajectory section can also be recorded using other localization methods, for example using landmark-based localization.
  • the trajectory section can also be recorded as a planned trajectory of the vehicle, for example by a navigation unit or a unit for planning an autonomous control of the vehicle.
  • the trajectory section can be recorded in global or relative coordinate systems.
  • the determined locating offset corresponds in particular to a ⁇ / ' as vector which designates a vector from a measured position to an actual position.
  • the positions can be determined in a global coordinate system or in a local one Coordinate system can be specified relative to a specific reference point, typically depending on the method used to determine the position.
  • the detected offset of the trajectory can be corrected by the location offset so that it matches the preferred line as well as possible and therefore the one actually traveled
  • the location offset determined in the method can be output, for example by transmission to a driver assistance system or another device.
  • the constant bias of the position measurement compared to the map data, determined with the location offset, can now be used to correct the detected trajectory section of the vehicle. In this way it can be achieved that the acquired trajectory essentially,
  • the location offset can be determined in the vehicle coordinate system or another relative coordinate system and / or in a global coordinate system. If there is information about an expected localization error, for example about its type or form, the system can be limited for the method, for example to only determine a location offset in a global coordinate system. This can be the case for recipients for a global coordinate system.
  • Navigation satellite system may be useful.
  • a relative localization error can be determined in a local coordinate system.
  • Trajectory section a variety of temporally successive position measurements, especially in a global coordinate system. This advantageously describes the movement of the vehicle using discrete position measurements.
  • the large number of measurements allows a reliable statistical evaluation of the data in order to precisely determine the course of the vehicle's journey despite possible fluctuations.
  • the detected trajectory section is compared with the preferred line in order to determine the location offset for correcting the position measurement for the trajectory section.
  • the method assumes in particular that a vehicle always moves on average close to the preferred line when traveling along a trajectory section. Smaller deviations to the left or to the right compensate for an averaging or another statistical evaluation over a temporal or spatial interval. In order to be able to make this assumption, sufficient data about the trajectory must be available for statistical analysis.
  • the detected trajectory section has position measurements during a certain time interval, over a certain route and / or a certain route length.
  • the detected preferred line therefore advantageously has a certain spatial or temporal length, which is defined, for example, by a certain number of measurements, the detection over a certain time period or along a certain path length.
  • data are available over an appropriate length of the route or over an appropriate length of a time interval, which are compared with the preferred line. For example, it can be assumed that with averaging over at least 20 seconds, preferably at least 30 seconds, the deviations are already significantly reduced.
  • measurements over a certain length of the trajectory section can be taken into account, for example over at least 150 m, preferably at least 250 m.
  • the length of the trajectory section can also be determined by a combination of spatial and temporal length if, for example, detection over a certain period of time and at the same time a minimum spatial length is required for usable detection.
  • the trajectory section is captured by means of a sliding window algorithm, in particular a so-called “sliding window”.
  • sliding window a sliding window algorithm
  • the trajectory section last traveled on in each case is advantageously taken into account in order to determine the location offset.
  • Location offset is determined for a specific point in time or a specific position, wherein the captured trajectory section only comprises data that are within a
  • a certain period of time or length range before In this way "moves" the captured trajectory section constantly while the vehicle is moving or as time passes.
  • a temporal or spatial length is defined for the acquisition of the trajectory section.
  • Process data outside this window are not taken into account, so that, for example, a deviation from the preferred line only influences the calculation over a limited period of time. Conversely, the width of the window is chosen so that a sufficient database is available for statistical analysis.
  • the width of the sliding window, within which the trajectory section is captured corresponds in particular to the temporal or local length of the captured
  • Trajectory section It can be fixed or determined dynamically. For example, different widths can be selected depending on the driving situation or the speed of the vehicle.
  • the detected trajectory section is smoothed when the trajectory section and the preferred line are compared. This means, for example, that statistical fluctuations in the trajectory are no longer taken into account. Alternatively or additionally, a large number of deviations of the detected trajectory section from the
  • Preferred line section can be determined and averaged. Additional statistical methods can be used alternatively or additionally, for example with a weighting in which deviations from the preferred line are taken into account to a greater or lesser extent depending on their amplitude.
  • a preferred line section is determined which corresponds to a section of the traffic route traveled by the vehicle. This will capture the
  • Trajectory section advantageously compared with the matching section of the preferred line.
  • the preferred line section is determined in a manner known per se. For example, it can be assumed that the vehicle is in the closest position to a preferred line.
  • the preferred line section can also be determined on the basis of a planned route for the vehicle, provided that it can be assumed that the vehicle is actually moving along this route.
  • when determining the preferred line section it is determined which lane of the traffic route the vehicle is on. This can be
  • the current lane can be determined in a manner known per se, for example on the basis of video data from a camera, by means of another detector such as lidar, radar or on the basis of information from a navigation system which specifies the lane to be used.
  • an odometry method can be carried out or signals relating to the selection of the lane, for example the actuation of a
  • a lateral position of the vehicle relative to the traffic route is recorded.
  • the so-called "lateral placement" of the vehicle is determined.
  • Preferred line deviates. This allows the measurement to be refined by comparing the measured trajectory section with the actually traveled trajectory on the traffic route.
  • Methods known per se can also be used here, for example by means of a camera, a radar or lidar scanner, local devices for determining the position or other sensors.
  • Vehicle makes a lane change, cuts a curve or in one
  • a filter can be implemented by means of which the method is only switched on in those areas in which it can be assumed as certain that the vehicle is actually moving along the preferred line. Captured in such areas
  • the trajectory section can then be used for referencing and for comparison with the preferred line.
  • the usable area is determined on the basis of a deviation intention for the vehicle.
  • a deviation intention for the vehicle In particular, an intention to perform a driving maneuver such as changing lanes, overtaking or evasive action is detected or the completion of such a driving maneuver is detected. This allows the usable area
  • the usable area is determined on the basis of a course of the traffic route, for example on the basis of the position of a curve.
  • Deviation from the preferred line is to be expected. This is the case, for example, with bends, at intersections, at construction sites, roundabouts, exits or positions where parking vehicles have to be avoided.
  • the usable area is determined using a machine learning process.
  • the usable areas can advantageously be determined particularly reliably.
  • the machine learning process can be carried out in a manner known per se.
  • training takes place on the basis of data recorded in the past, in which, for example, deviations from the preferred line depending on certain properties of the traffic route or other conditions were detected.
  • Trajectory section determined and the length of the trajectory section detected is determined based on the measurement accuracy. This allows the trajectory section
  • the measurement inaccuracy can be determined, for example, on the basis of a standard deviation or another measure for the uncertainty of a position measurement.
  • the device used to record the trajectory section can also provide the data required for this. For example, a recipient for a global
  • Navigation satellite system Provide information about how many navigation satellites are currently visible, how well their signal is received and what effects this has on the accuracy of the acquisition of the trajectory section.
  • a change in the measurement uncertainty for the detection of an initial trajectory is detected and, depending on the change, the detection of the trajectory section is initiated or ended. In this way, it can advantageously be detected when the conditions for detecting the trajectory section and
  • the measurement uncertainty changes, it can be determined that a measured position or trajectory has a greater or lesser statistical uncertainty. Furthermore, the change in the measurement uncertainty can lead to a change in the systematic offset between the measured and actual trajectory. In particular, such a change can therefore be determined if the deviation of the detected positions from the actual position changes abruptly and therefore another
  • Location offset must be used for correction. Such changes can occur for example, come when the number of visible navigation satellites changes at a time.
  • the change in the measurement uncertainty can be recorded in different ways, for example on the basis of data which are recorded by a unit for recording the
  • Trajectory section are checked whether sudden position changes occur, especially if they are recognized as implausible in a physical model. For example, it can be detected if a sudden change in position of the vehicle is measured, although it does not move or at a lower speed, or if the direction of the change in position does not change with the other movement of the vehicle
  • Vehicle matches In particular, odometry is used to detect the actual movement of the vehicle, or the plausibility of the detected is
  • the time derivative of the detected vehicle movement along the trajectory section can be determined. If a certain threshold for the
  • Position change depending on the time is exceeded, this can be interpreted as a "jump" and evaluated as an indication of a new location offset to be determined.
  • a reset can be carried out when the trajectory section is recorded,
  • a defective calibration of a unit for detecting the trajectory section can be determined and / or characterized on the basis of the determined location offset.
  • Such calibration defects typically lead to systematic errors in the detection of the trajectory section, which can be recognized by the method according to the invention.
  • the type of the calibration defects typically lead to systematic errors in the detection of the trajectory section, which can be recognized by the method according to the invention.
  • Component is incorrectly calibrated or how the calibration needs to be corrected.
  • An incorrect calibration can be provided on the basis of the determined one
  • the location offset is determined by an external unit, for example by an external server.
  • the external unit is technically connected to the vehicle and receives the detected one
  • map data can be transmitted from the vehicle to the external unit or, conversely, the latter can provide map data for the vehicle.
  • the external unit can now determine the location offset and, if necessary, transmit it to the vehicle.
  • the location offset alternatively or additionally includes a correction of the alignment of the vehicle.
  • the correction can therefore not only be applied to the trajectory driven by the vehicle or its position, but also its orientation in space.
  • the combination of position and orientation is typically referred to as a "pose” and is often determined together.
  • the systematic errors that may also occur here, in particular over certain time periods, can also be corrected using the method according to the invention.
  • the orientation of the vehicle typically correlates with a movement orientation, that is to say the vehicle is oriented in the direction of the movement during a straight-ahead movement.
  • the position determination system is characterized in that the computing unit is set up to determine a location offset on the basis of a comparison of the detected trajectory section and the preferred line, to determine a corrected trajectory section on the basis of the location offset and the detected trajectory section and to determine the location offset in this way that a deviation between the preferred line and the corrected trajectory section is optimized.
  • the device according to the invention is particularly designed to implement the method according to the invention described above.
  • the device thus has the same advantages as the method according to the invention.
  • An embodiment of the position determination system comprises a detection unit coupled to the computing unit for detecting environmental data in an environment of the vehicle.
  • the computing unit is also set up to determine a usable area of the trajectory section on the basis of the recorded environmental data, on the basis of which the comparison with the preferred line is carried out.
  • the location offset is advantageously determined particularly reliably, since, for example, unusable areas in which the actual position of the vehicle clearly deviates from the preferred line can be excluded from the evaluation.
  • Figure 1 shows a vehicle with an embodiment of the invention
  • Figure 2 shows the vehicle when traveling along a traffic route
  • FIG. 3 shows an embodiment of the method according to the invention.
  • the vehicle 1 comprises a position determination unit 5, which in the exemplary embodiment is based on a global navigation satellite system, in particular the global one
  • GPS positioning system It also includes a detection unit 2, which in the
  • Embodiment comprises a camera 3 and a preprocessing unit 4.
  • the detection unit 2 can alternatively or additionally comprise any desired sensor devices, such as LI DAR or RADAR scanners, time-of-flight cameras, stereo cameras, infrared cameras, ultrasound or other sensors.
  • the vehicle 1 further comprises a computing unit 6, which comprises a navigation unit 8 and with the detection unit 2, the position determination unit 5 and one
  • Driver assistance system 7 is coupled.
  • the vehicle 1 travels on a traffic route 22 into the one indicated by the arrow 25
  • Two lanes are formed on the traffic route 22, which are defined by the solid lateral boundaries of the traffic route 22 and a dashed median lane 23.
  • the vehicle 1 is on the right lane in the direction of travel 25.
  • a preferred line 24 is drawn in the exemplary embodiment runs essentially centrally along the lane of the vehicle 1.
  • the vehicle 1 is steered along an actual trajectory, which runs essentially centrally in the traffic route 22 and therefore largely corresponds to the preferred line 24.
  • the actually driven trajectory of the vehicle 1 therefore differs from the preferred line 24 in the exemplary embodiment by only slight statistical deviations in the lateral direction.
  • the navigation unit 8 provides map data in the vehicle 1, that is, it functions as the map data preparation unit 8, which includes information about the course of the traffic route 22, its division into the lanes, the course of the center line 23 and the course of the preferred line 24 .
  • map data are provided by an external unit which supplement or alternatively provide this information.
  • the acquisition from the external unit takes place via a data link, for example based on a request from the vehicle or by automatic transmission of relevant map data to vehicle 1.
  • a known “streaming” of the map data relevant to vehicle 1 is carried out, in particular via the Internet.
  • the geographic position 26 of the vehicle is determined by the position determination unit 5 of the vehicle 1 at regular intervals 1 determined and transmitted to the computing unit 6.
  • the determination is carried out using GPS in global coordinates.
  • a different position determination can be carried out, for example by means of landmark-based positioning, and the position can also be determined in a relative coordinate system.
  • the detected positions 26 of the vehicle 1 do not follow the trajectory of the vehicle 1 that is actually driven or the preferred line 24, but are offset relative to it. Furthermore, the detected positions 26 have statistical scattering, which takes into account that the actual trajectory of the vehicle 1 the preferred line 24 does not correspond exactly, unlike for example for a
  • Deviations from the preferred line 24 are designed such that they only occur briefly compared to the length of the entire trajectory section shown.
  • the arithmetic unit 6 uses the detected positions 26 to determine a trajectory section which, in the exemplary embodiment, comprises all the positions 26 shown.
  • the length of the trajectory section is defined in the exemplary embodiment as the amount of
  • Position measurements that are recorded within a certain time interval here 30 s.
  • a different time interval can be provided, for example 1 min, or the length of the trajectory section can be defined on the basis of its spatial length and include, for example, a travel path of 200 m or 400 m.
  • the detection of the trajectory section takes place by means of a “sliding window”, in which the detected trajectory section constantly shifts with the passage of time and the continuous movement of the vehicle 1.
  • the temporal and / or spatial definition of the length of the trajectory section can be referred to as the “width” of the sliding window. This width is constant in the exemplary embodiment, but it can also be designed dynamically in further exemplary embodiments, for example depending on a driving situation, a speed, or one provided by the position determination unit 5
  • the arithmetic unit 6 determines a location offset 28 for the detected trajectory section by determining a section of the preferred line 24 that corresponds to the detected trajectory section. In the exemplary embodiment shown, this is essentially the entire preferred line 24 shown. Here, the assumption is made that the actually driven trajectory of the vehicle 1 on the traffic route 22 can be approximated well by the preferred line 24. For the determining relevant section of the preferred line 24 in the exemplary embodiment, the detection unit 2 is also used to determine which lane of the traffic route 22 the vehicle 1 is on.
  • a comparison is then carried out in which the computing unit 6 determines deviations of the detected positions 26 with respect to the preferred line 24 or the determined preferred line section.
  • this is the geometric distance of the detected positions 26 from the closest point preferred line 24; however, other dimensions may be used in other embodiments.
  • a locating offset 28 is determined, which corresponds to a bias vector 28 and describes a spatial displacement of the detected positions 26 in such a way that they are optimally displaced in the sense of a minimal deviation from the preferred line.
  • the computing unit 6 corrects the detected positions 26 of the trajectory section in order to arrive at corrected positions 27.
  • FIG. 3 shows the shift of the detected positions 26 by the locating offset 28 towards the corrected positions 27.
  • the corrected positions 27 follow the preferred rail 24 much better than the detected positions 26, that is, it becomes a single one
  • a rotation by a specific angle can also be determined in accordance with the same optimization task. This allows a correction not only for a translational correction of the detected positions 26 compared to the corrected positions 27, but also a rotational correction.
  • the corrected positions 27 in the region of the curve of the preferred line 24 differ significantly from the latter. This can occur, for example, when the vehicle 1 “cuts” the curve and therefore does not travel on the preferred line 24. If such an event has only a short duration, so that only a few recorded positions 26 are recorded while the vehicle 1 deviates from the preferred line 24, there is only a slight impact on the determination of the locating offset 28
  • Positions 26 are therefore not filtered in the exemplary embodiment in order to exclude this position.
  • the computing unit 6 receives data if the actual deviation from the vehicle trajectory traversed by the preferred line 24 from the recorded data. For example, the computing unit 6 uses data from the recording unit 2 to recognize situations in which there is a deviation from the preferred line 24, such as cutting a curve, changing lanes, evading or overtaking. The positions 26 detected in this area are then excluded from the determination of the locating offset 28.
  • the computing unit 6 determines a usable area of the detected trajectory section, this usable area also having to meet the conditions for a certain length of the trajectory section usable for the method. Those positions 26 that were recorded in areas that cannot be used, for example in the area of a curve, are rejected. Furthermore, data from the detection unit 2 are used to identify when the driver of the vehicle 1 intends to deviate from the preferred line 24, for example when a turn signal is activated or a rapid one is activated
  • Driver assistance system 27 are detected, such as an overtaking assistant.
  • a machine learning method can be used to distinguish unusable from usable regions of the detected trajectory section.
  • the system is trained in a manner known per se on the basis of historical data and areas can automatically be recognized in which a deviation from the preferred line 24 is to be expected.
  • Such areas can have, for example, vehicles parked at the edge of the traffic route 22 or certain devices for regulating the traffic which make evasive action necessary.
  • Preferred line 24 is recognized, in the optimization of the locating offset 28 for different subsets of the detected positions 26, their deviation from different preferred lines 24 is determined.
  • the detection unit 2 of the vehicle 1 is also used to determine the position of the vehicle 1 on the traffic route 22, in particular in the lateral direction, and to take it into account when determining the deviation of the measured positions 26 from the preferred line 24, where in the Relative to the preferred line 24, the vehicle 1 is actually located. In this way, the locating offset 28 can be determined more precisely since the deviation from the actual position is now determined can, without having to accept the assumption that the position of the vehicle 1 is on the preferred line 24.
  • Trajectory section with the sliding window can be interrupted if one
  • Change in the location offset 28 is detected. Such a change is detected on the basis of data from the position determination unit 5, which for example a change in the
  • the change is also detected when the detected trajectory section exhibits a sudden change in position which the system recognizes as not plausible.
  • a sudden change in position can be detected when the conditions for detecting the vehicle position change.
  • the change in position can be checked to determine whether it appears to be physically possible and / or whether it is consistent with odometry data or other data of the vehicle 1. If this is not the case, there is a condition in which the trajectory section is completely newly acquired. It is therefore a "reset in the detection of the trajectory section with the sliding window method and the trajectory section is completely newly acquired.
  • Map data preparation unit navigation unit

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé servant à déterminer une trajectoire d'un véhicule (1), consistant à acquérir des données cartographiques concernant une voie de circulation (22) sur laquelle le véhicule (1) se déplace, les données cartographiques contenant une ligne préférentielle (24) pour le parcours de la voie de circulation (22). Un tronçon de trajectoire du véhicule (1) est détecté. Un décalage de positionnement (28) est déterminé sur la base d'une comparaison entre le tronçon de trajectoire et la ligne préférentielle (24), et un tronçon de trajectoire corrigé est déterminé sur la base du décalage de positionnement (28) et du tronçon de trajectoire détecté. Le décalage de positionnement (28) est déterminé de manière à optimiser un écart entre la ligne préférentielle (24) et le tronçon de trajectoire corrigé. Le système de détermination de position servant à déterminer une trajectoire d'un véhicule (1) comprend une unité d'acquisition (8) de données cartographiques servant à acquérir des données cartographiques concernant une voie de circulation (22) sur laquelle le véhicule (1) se déplace, les données cartographiques contenant une ligne préférentielle (24) pour le parcours de la voie de circulation (22). Il comprend en outre une unité de détermination de position (5) servant à détecter un tronçon de trajectoire du véhicule (1), et une unité de calcul (6) raccordée à l'unité de détermination de position (5) et à l'unité d'acquisition (8) de données cartographiques. L'unité de calcul (6) est conçue pour déterminer un décalage de positionnement (28) sur la base d'une comparaison entre le tronçon de trajectoire et la ligne préférentielle (24), pour déterminer un tronçon de trajectoire corrigé sur la base du décalage de positionnement (28) et du tronçon de trajectoire détecté, et pour déterminer le décalage de positionnement (28) de manière à optimiser un écart entre la ligne préférentielle (24) et le tronçon de trajectoire corrigé.
PCT/EP2019/082485 2018-12-17 2019-11-25 Procédé et système servant à déterminer une trajectoire corrigée d'un véhicule WO2020126338A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980083784.XA CN113165661A (zh) 2018-12-17 2019-11-25 用于确定车辆的修正轨迹的方法和系统
EP19816216.6A EP3898368B1 (fr) 2018-12-17 2019-11-25 Procédé et système servant à déterminer une trajectoire corrigée d'un véhicule

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102018221864.1 2018-12-17
DE102018221864.1A DE102018221864A1 (de) 2018-12-17 2018-12-17 Verfahren und System zum Bestimmen einer Trajektorie eines Fahrzeugs

Publications (1)

Publication Number Publication Date
WO2020126338A1 true WO2020126338A1 (fr) 2020-06-25

Family

ID=68806709

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2019/082485 WO2020126338A1 (fr) 2018-12-17 2019-11-25 Procédé et système servant à déterminer une trajectoire corrigée d'un véhicule

Country Status (4)

Country Link
EP (1) EP3898368B1 (fr)
CN (1) CN113165661A (fr)
DE (1) DE102018221864A1 (fr)
WO (1) WO2020126338A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113806465A (zh) * 2021-09-22 2021-12-17 公安部交通管理科学研究所 基于新能源汽车轨迹数据的卡口位置经纬度纠偏方法
US11841708B2 (en) * 2020-02-28 2023-12-12 Zoox, Inc. System and method for adjusting a planned trajectory of an autonomous vehicle

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116534059B (zh) * 2023-07-04 2023-09-08 深圳海星智驾科技有限公司 自适应感知路径决策方法、装置、计算机设备及存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008023242A1 (de) * 2007-05-29 2008-12-04 Continental Teves Ag & Co. Ohg Map matching für Sicherheitsanwendungen
DE102010005293A1 (de) 2009-01-26 2010-09-02 GM Global Technology Operations, Inc., Detroit System und Verfahren zur Spurpfadschätzung unter Verwendung einer Sensorvereinigung
DE102015214338A1 (de) 2015-07-29 2017-02-02 Volkswagen Aktiengesellschaft Bestimmung einer Anordnungsinformation für ein Fahrzeug
US20170247032A1 (en) 2016-02-26 2017-08-31 GM Global Technology Operations LLC System and method for providing a corrected lane following path through a curve for trailering vehicles
DE102017005020A1 (de) * 2017-05-26 2017-12-14 Daimler Ag Verfahren zur Bestimmung einer Position eines Fahrzeugs
DE102016213782A1 (de) 2016-07-27 2018-02-01 Volkswagen Aktiengesellschaft Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn
DE102016213783A1 (de) 2016-07-27 2018-02-01 Volkswagen Aktiengesellschaft Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeugs relativ zu den Fahrstreifen einer Fahrbahn
DE102017006142A1 (de) 2017-06-29 2018-02-22 Daimler Ag Verfahren zur Lokalisierung eines Fahrzeuges innerhalb eines Fahrstreifens

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110320163A1 (en) * 2008-11-06 2011-12-29 Volvo Technology Corporation Method and system for determining road data
CN102632891B (zh) * 2012-04-06 2014-09-17 中国人民解放军军事交通学院 无人驾驶车辆实时跟踪行驶轨迹的计算方法
DE102012023107B4 (de) * 2012-11-27 2017-06-29 Audi Ag Verfahren zum Betrieb eines Fahrerassistenzsystems eines Kraftfahrzeugs und Kraftfahrzeug
DE102014103556B4 (de) * 2013-03-15 2020-06-18 Infineon Technologies Ag Sensor-Selbstdiagnose unter Einsatz mehrerer Signalwege
US9240123B2 (en) * 2013-12-13 2016-01-19 Here Global B.V. Systems and methods for detecting road congestion and incidents in real time
JP6229523B2 (ja) * 2014-02-12 2017-11-15 株式会社デンソー 自車走行位置特定装置及び自車走行位置特定プログラム
DE102015206342A1 (de) * 2014-04-09 2015-10-15 Continental Teves Ag & Co. Ohg Positionskorrektur eines Fahrzeugs durch Referenzierung zu Objekten im Umfeld
US9934688B2 (en) * 2015-07-31 2018-04-03 Ford Global Technologies, Llc Vehicle trajectory determination
JP6520597B2 (ja) * 2015-09-16 2019-05-29 株式会社デンソー 車両位置補正装置
DE102015220360A1 (de) * 2015-10-20 2017-04-20 Robert Bosch Gmbh Verfahren zur Auswahl einer optimierten Trajektorie
US9952056B2 (en) * 2016-03-11 2018-04-24 Route4Me, Inc. Methods and systems for detecting and verifying route deviations
CN108628324B (zh) * 2018-07-12 2021-03-02 中国科学院深圳先进技术研究院 基于矢量地图的无人车导航方法、装置、设备及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008023242A1 (de) * 2007-05-29 2008-12-04 Continental Teves Ag & Co. Ohg Map matching für Sicherheitsanwendungen
DE102010005293A1 (de) 2009-01-26 2010-09-02 GM Global Technology Operations, Inc., Detroit System und Verfahren zur Spurpfadschätzung unter Verwendung einer Sensorvereinigung
DE102015214338A1 (de) 2015-07-29 2017-02-02 Volkswagen Aktiengesellschaft Bestimmung einer Anordnungsinformation für ein Fahrzeug
US20170247032A1 (en) 2016-02-26 2017-08-31 GM Global Technology Operations LLC System and method for providing a corrected lane following path through a curve for trailering vehicles
DE102016213782A1 (de) 2016-07-27 2018-02-01 Volkswagen Aktiengesellschaft Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn
DE102016213783A1 (de) 2016-07-27 2018-02-01 Volkswagen Aktiengesellschaft Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeugs relativ zu den Fahrstreifen einer Fahrbahn
DE102017005020A1 (de) * 2017-05-26 2017-12-14 Daimler Ag Verfahren zur Bestimmung einer Position eines Fahrzeugs
DE102017006142A1 (de) 2017-06-29 2018-02-22 Daimler Ag Verfahren zur Lokalisierung eines Fahrzeuges innerhalb eines Fahrstreifens

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
YINLOU ET AL: "Map-MatchingforLow-Sampling-RateGPSTrajectories", 4 November 2009 (2009-11-04), XP055667613, Retrieved from the Internet <URL:https://dl.acm.org/doi/pdf/10.1145/1653771.1653820?download=true> [retrieved on 20200212] *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11841708B2 (en) * 2020-02-28 2023-12-12 Zoox, Inc. System and method for adjusting a planned trajectory of an autonomous vehicle
CN113806465A (zh) * 2021-09-22 2021-12-17 公安部交通管理科学研究所 基于新能源汽车轨迹数据的卡口位置经纬度纠偏方法

Also Published As

Publication number Publication date
CN113165661A (zh) 2021-07-23
EP3898368A1 (fr) 2021-10-27
EP3898368B1 (fr) 2023-10-04
DE102018221864A1 (de) 2020-06-18

Similar Documents

Publication Publication Date Title
EP3584663B1 (fr) Procédé de guidage transversal automatique d&#39;un véhicule suiveur dans un peloton de véhicules
DE102020118187B4 (de) System und Verfahren zum Kalibrieren einer Lenkradneutralstellung
EP3443301B1 (fr) Procédé et système de détermination d&#39;une position globale d&#39;un premier repère
DE102010005293B4 (de) System und Verfahren zur Spurpfadschätzung unter Verwendung einer Sensorvereinigung
DE102013105046B4 (de) Zielspurauswahlverfahren mittels Navigationseingabe in Straßenwechselszenarien
EP3094530B1 (fr) Procédé et système pour évaluer le tracé d&#39;une voie de circulation
EP2819901B1 (fr) Procédé et dispositif de détermination de la vitesse et/ou de la position d&#39;un véhicule
DE102007041121B4 (de) Verfahren und Vorrichtung zum Verarbeiten von Sensordaten für ein Fahrerassistenzsystem eines Fahrzeugs
DE102018115813A1 (de) Verfahren und systeme zum lokalisieren eines fahrzeugs
EP3142091B1 (fr) Procede de planification d&#39;un stationnement assiste
EP3298541A1 (fr) Procédé d&#39;estimation de files de circulation
EP3898368B1 (fr) Procédé et système servant à déterminer une trajectoire corrigée d&#39;un véhicule
DE102014215570B4 (de) Fahrzeugnavigationssystem
DE102016213817B4 (de) Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn
EP3491339A1 (fr) Procédé, dispositif et support de stockage lisible par ordinateur contenant des instructions permettant de déterminer la position latérale d&#39;un véhicule par rapport aux voies de circulation d&#39;une chaussée
DE102016209232B4 (de) Verfahren, Vorrichtung und computerlesbares Speichermedium mit Instruktionen zur Bestimmung der lateralen Position eines Fahrzeuges relativ zu den Fahrstreifen einer Fahrbahn
DE102020107349A1 (de) Verfahren und vorrichtung zur dynamischen gierratenabweichungsschätzung
EP3729138B1 (fr) Procédé de détermination assistée par satellites d&#39;une position d&#39;un véhicule
EP3610224B1 (fr) Procédé, dispositif et support d&#39;enregistrement lisible par ordinateur comprenant des instructions servant à estimer une position d&#39;un véhicule automobile
DE102018212219A1 (de) Überprüfen einer geographischen Karte
WO2017102192A1 (fr) Procédé amélioré de détermination de la construction de bord d&#39;une chaussée pour la localisation de véhicules automobiles
EP4158611A1 (fr) Assistant de voie d&#39;urgence
DE102016207181B4 (de) Verfahren und System zum Bestimmen einer Position eines Fahrzeugs auf einer Fahrbahn
EP1696207B1 (fr) Procédé et système destinés à la détermination de données de position d&#39;un objet
EP2172826B1 (fr) Dispositif et procédé destinés à déterminer un parcours de voie de circulation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19816216

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2019816216

Country of ref document: EP

Effective date: 20210719